commit 3e613ea87011ef3283edbd62f2bde1587ae8397f Author: ModelHub XC Date: Sun Aug 16 22:19:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RECAST-Qwen-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..811955d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RECAST-Qwen-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7b02429 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: wenhaoliu123/RECAST-Qwen-sft +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + + + + +static quants of https://huggingface.co/wenhaoliu123/RECAST-Qwen-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RECAST-Qwen-sft-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RECAST-Qwen-sft-GGUF/resolve/main/RECAST-Qwen-sft.f16.gguf) | f16 | 15.3 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/RECAST-Qwen-sft.IQ4_XS.gguf b/RECAST-Qwen-sft.IQ4_XS.gguf new file mode 100644 index 0000000..f7a1805 --- /dev/null +++ b/RECAST-Qwen-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:913b70c831ead085be7af691e7bc71bef9be7753ba3f06ca64252d2a9c8a2aa7 +size 4248371616 diff --git a/RECAST-Qwen-sft.Q2_K.gguf b/RECAST-Qwen-sft.Q2_K.gguf new file mode 100644 index 0000000..86f2ca6 --- /dev/null +++ b/RECAST-Qwen-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b65ebbf9794758197b0cc459082cdc26459c25e90ed6ccbfecb4b22fcf84380 +size 3014301632 diff --git a/RECAST-Qwen-sft.Q3_K_L.gguf b/RECAST-Qwen-sft.Q3_K_L.gguf new file mode 100644 index 0000000..35de29f --- /dev/null +++ b/RECAST-Qwen-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1972634d0a521133ab93da628df65617466cb2554c046a3d6748d1bb858e372 +size 4086676672 diff --git a/RECAST-Qwen-sft.Q3_K_M.gguf b/RECAST-Qwen-sft.Q3_K_M.gguf new file mode 100644 index 0000000..7833ad2 --- /dev/null +++ b/RECAST-Qwen-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13baa9544be2c1abeec9bab6acf7e5169d229bd0514e77cbbca05fcd3b5d55be +size 3806608576 diff --git a/RECAST-Qwen-sft.Q3_K_S.gguf b/RECAST-Qwen-sft.Q3_K_S.gguf new file mode 100644 index 0000000..b81a759 --- /dev/null +++ b/RECAST-Qwen-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61cc8c95b4aee7ee2806cd5e282c00b409ddaaa33b7375b6727121e29fd94230 +size 3490585792 diff --git a/RECAST-Qwen-sft.Q4_K_M.gguf b/RECAST-Qwen-sft.Q4_K_M.gguf new file mode 100644 index 0000000..6bf5878 --- /dev/null +++ b/RECAST-Qwen-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9dba8db4768639bfaf6a9ef800adbac7c2722320bab8b6eb4fd3b90ae228e1e +size 4681102432 diff --git a/RECAST-Qwen-sft.Q4_K_S.gguf b/RECAST-Qwen-sft.Q4_K_S.gguf new file mode 100644 index 0000000..587a8cd --- /dev/null +++ b/RECAST-Qwen-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afae597ad07848099bb60e6fba23e494e2bf5a651318abad30dba5a63cbd67d9 +size 4455797856 diff --git a/RECAST-Qwen-sft.Q5_K_M.gguf b/RECAST-Qwen-sft.Q5_K_M.gguf new file mode 100644 index 0000000..91cf2ef --- /dev/null +++ b/RECAST-Qwen-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5264ae36a9b841bfb82e68a18ef500ca8b665e8f0b3c5b736fc2356539548f3d +size 5442682720 diff --git a/RECAST-Qwen-sft.Q5_K_S.gguf b/RECAST-Qwen-sft.Q5_K_S.gguf new file mode 100644 index 0000000..103a625 --- /dev/null +++ b/RECAST-Qwen-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04794f0060ad6588e65b6832fc7ec110a57a633a6d2f2930cae268cc57deae50 +size 5313027936 diff --git a/RECAST-Qwen-sft.Q6_K.gguf b/RECAST-Qwen-sft.Q6_K.gguf new file mode 100644 index 0000000..c86acd4 --- /dev/null +++ b/RECAST-Qwen-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eff27aa545257f76be1c00d67cfab8b4a0b3a398ab6dd5a46ecb722c720b6be6 +size 6251861792 diff --git a/RECAST-Qwen-sft.Q8_0.gguf b/RECAST-Qwen-sft.Q8_0.gguf new file mode 100644 index 0000000..5aa2b37 --- /dev/null +++ b/RECAST-Qwen-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197010e611f26bd010f3132271e165905859233e25714a6d8607a92cd2d876c7 +size 8095500704 diff --git a/RECAST-Qwen-sft.f16.gguf b/RECAST-Qwen-sft.f16.gguf new file mode 100644 index 0000000..cc5997a --- /dev/null +++ b/RECAST-Qwen-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091402b469299bca31a8ae194c317292469a498a512b455bdf82f534a07640d5 +size 15232167584